Enhancing Sentence Relation Modeling with Auxiliary Character-level Embedding
This work addresses sentence relation modeling for natural language processing applications, representing an incremental improvement over existing methods.
The paper tackles the challenge of modeling complex semantic relations like entailment and contradiction in sentence pairs by proposing a neural network architecture that combines pre-trained word embeddings with auxiliary character embeddings. Experimental results show the approach consistently outperforms existing methods on standard datasets.
Neural network based approaches for sentence relation modeling automatically generate hidden matching features from raw sentence pairs. However, the quality of matching feature representation may not be satisfied due to complex semantic relations such as entailment or contradiction. To address this challenge, we propose a new deep neural network architecture that jointly leverage pre-trained word embedding and auxiliary character embedding to learn sentence meanings. The two kinds of word sequence representations as inputs into multi-layer bidirectional LSTM to learn enhanced sentence representation. After that, we construct matching features followed by another temporal CNN to learn high-level hidden matching feature representations. Experimental results demonstrate that our approach consistently outperforms the existing methods on standard evaluation datasets.